Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Region-based Q-learning for intelligent robot systems

지능형 로보트 시스템을 위한 영역기반 Q-learning

  • Kim, Jae-Hyeon (Dept. of Electronic Engineering, Hanyang University) ;
  • Seo, Il-Hong (Dept. of Electronic Engineering, Hanyang University)
  • Published : 1997.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

It is desirable for autonomous robot systems to possess the ability to behave in a smooth and continuous fashion when interacting with an unknown environment. Although Q-learning requires a lot of memory and time to optimize a series of actions in a continuous state space, it may not be easy to apply the method to such a real environment. In this paper, for continuous state space applications, to solve problem and a triangular type Q-value model\ulcorner This sounds very ackward. What is it you want to solve about the Q-value model. Our learning method can estimate a current Q-value by its relationship with the neighboring states and has the ability to learn its actions similar to that of Q-learning. Thus, our method can enable robots to move smoothly in a real environment. To show the validity of our method, navigation comparison with Q-learning are given and visual tracking simulation results involving an 2-DOF SCARA robot are also presented.

Keywords

References

  1. IEEE Conference on R&A v.1 Learning behavior control by reinforcent for an autonomous mobilc robot M. A. Salichs;E. A. Puente;D. Gachet;J. R. Pementel
  2. IEEE Trans. on Neural Networks v.3 no.5 Learning and tuning fuzzy logic controllers through reinforcement H. Berenji;P. Khedkar
  3. Proc. of the Ninth National Conference on Artificial Intelligence Programming robots using reinforcement learning and teaching L. J. Lin
  4. Machine Learning Practical Issues in Temporal Difference Learning G. Tesauro
  5. Machine Learning v.8 Q-learning, technical note C. Watkins;P. Dayan
  6. Ph.D. Thesis, University of Combridge Learning from delayed rewards C. Watkins
  7. IEEE Conference on R&A v.1 Fuzzy Q-learning and dynamical fuzzy Q-learning P. Y. Glorennec
  8. IEEE Conference on R&A v.1 A new approach for fuzzy dynamic programming H. R. Berenji;Fuzzy Q learning
  9. IEEE Conference on Fuzzy Systems v.1 Fuzzy interpolation based Q-leaning with continuous states and actions T. Horiuchi;A. Fujino;O. Katai;T. Sawaragi